FRESH

FRESH is shared URL freshness intelligence for AI agents. Before re-fetching, re-scraping, re-rendering, or re-embedding a URL, ask whether the previously seen version is probably still fresh enough to reuse.

Production base URL:https://fresh-api-production-c783.up.railway.app

MCP endpoint:https://fresh-api-production-c783.up.railway.app/mcp

- REUSE— cached knowledge is probably still fresh enough
- REFETCH— the URL is likely stale enough to justify another retrieval
- UNKNOWN— evidence is insufficient; FRESH prefers uncertainty over false confidence

A local cache knows whenyoulast fetched something. It does not know whether the outside resource changed since then, nor what other callers recently observed. FRESH builds shared, privacy-safe URL change history from timestamps, ETags, Last-Modified values, and content hashes.

{"url":"https://example.com/docs/api","lastSeenAt":"2026-08-13T12:00:00Z","toleranceSeconds":3600}

{"url":"https://example.com/docs/api","observedAt":"2026-08-13T13:00:00Z","etag":"abc123","lastModified":"Wed, 13 Aug 2026 12:45:00 GMT","contentHash":"sha256:..."}

- fresh_check— decide whether to retrieve a URL again
- fresh_observe— report privacy-safe freshness evidence after retrieval

A core-tool invocation is evidence of use, not automatically proof of a genuine stranger. FRESH classifies candidate activity asKNOWN_VALIDATOR,LIKELY_VALIDATOR,CONTROLLED_TEST,UNKNOWN_MACHINE, orCREDIBLE_REAL_USE. OnlyCREDIBLE_REAL_USEadvances stranger milestones.

Our acceptance/smoke traffic usesX-Tollbooth-Internal: 1orX-Fresh-Internal: 1so it cannot earn stranger credit.

Every Railway deployment now performs live internal checks against the running service before/healthcan return 200. The gate exercises REST,UNKNOWN,REUSE,REFETCH, persistent observation reload, MCP initialize, MCP tool discovery, MCPfresh_check, and verifies that the controlled self-test does not increase the verified-stranger count.

v0.1.2 experimental production infrastructure. Priorities: conservative decisions, low latency, sub-penny economics, privacy-safe shared learning, REST + MCP, durable observations, and auditable real-use analytics.

Enable AI agents to get structured data from unstructured web with AgentQL.

Web scraping, crawling, and change detection with AI

Official Apify MCP server for AI agents to run Actors, extract website data, and automate web scraping and crawling workflows.

1GB Free Trial, World's Leading Proxy Service Platform, Efficient Data Collection

Discover, extract, and interact with the web - one interface powering automated access across the public internet.

Automate browser interactions in the cloud (e.g. web navigation, data extraction, form filling, and more)

Easy web data access. Simplified retrieval of information from websites and online sources.

Adds powerful web scraping and search capabilities to LLM clients like Cursor and Claude.

Real-time web data, structured for agents